commit e10f1c393c24f8f34b13afbc793f923a6b172e5f Author: ModelHub XC Date: Sat Jun 27 21:36:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: GGBondballs/Qwen2.5-7B-Instruct-awspo_gamma2 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..12dc87a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00004-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +model-00009-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +model-00006-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +model-00007-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +model-00008-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00002-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..93d1b52 --- /dev/null +++ b/README.md @@ -0,0 +1,52 @@ +--- +frameworks: +- Pytorch +license: Apache License 2.0 +tags: [] +tasks: +- text-generation + +#model-type: +##如 gpt、phi、llama、chatglm、baichuan 等 +#- gpt + +#domain: +##如 nlp、cv、audio、multi-modal +#- nlp + +#language: +##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa +#- cn + +#metrics: +##如 CIDEr、Blue、ROUGE 等 +#- CIDEr + +#tags: +##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他 +#- pretrained + +#tools: +##如 vllm、fastchat、llamacpp、AdaSeq 等 +#- vllm +--- +### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 +#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 + +SDK下载 +```bash +#安装ModelScope +pip install modelscope +``` +```python +#SDK模型下载 +from modelscope import snapshot_download +model_dir = snapshot_download('GGBondballs/Qwen2.5-7B-Instruct-awspo_gamma2') +``` +Git下载 +``` +#Git模型下载 +git clone https://www.modelscope.cn/GGBondballs/Qwen2.5-7B-Instruct-awspo_gamma2.git +``` + +

如果您是本模型的贡献者，我们邀请您根据模型贡献文档，及时完善模型卡片内容。

\ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..482ced4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 151657, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..de554be --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "/root/autodl-tmp/Qwen2.5-7B-Instruct", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..f9291c3 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"text-generation"} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..5855996 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "4.45.0" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00009.safetensors b/model-00001-of-00009.safetensors new file mode 100644 index 0000000..e286f07 --- /dev/null +++ b/model-00001-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4067b5b73fa3175a5a3a3a24027a08eb5560782e8d4bf6cdefa26e8764d32020 +size 1886423520 diff --git a/model-00002-of-00009.safetensors b/model-00002-of-00009.safetensors new file mode 100644 index 0000000..e06becf --- /dev/null +++ b/model-00002-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bc6fc21753792f912388a480134d751e10e1bf1454c2ddd197515ce3149f9bd +size 1864467800 diff --git a/model-00003-of-00009.safetensors b/model-00003-of-00009.safetensors new file mode 100644 index 0000000..859b02f --- /dev/null +++ b/model-00003-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6b877d816e0f8bce883b6447b8761f73bd6ae530a501305a52779d9ddc340a0 +size 1864467800 diff --git a/model-00004-of-00009.safetensors b/model-00004-of-00009.safetensors new file mode 100644 index 0000000..bd3f214 --- /dev/null +++ b/model-00004-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90a05fc062be9acbb68c08faae2738120a9dc578d6ea16d4a5be849f7e913803 +size 1864467824 diff --git a/model-00005-of-00009.safetensors b/model-00005-of-00009.safetensors new file mode 100644 index 0000000..96ef1b0 --- /dev/null +++ b/model-00005-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcc9aca8e1a86ffef0f20ec08090ba098557f69f9bae0ab79d1c23f9b36fa0e1 +size 1864467848 diff --git a/model-00006-of-00009.safetensors b/model-00006-of-00009.safetensors new file mode 100644 index 0000000..e327a3f --- /dev/null +++ b/model-00006-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47b6ec170d04f3de6eab2b932599ffcfa80eece6f6c9ddd785287ce574557db4 +size 1864467848 diff --git a/model-00007-of-00009.safetensors b/model-00007-of-00009.safetensors new file mode 100644 index 0000000..25d6f34 --- /dev/null +++ b/model-00007-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c57966e5d7cadc82d0e131244db99ed396e5338c32f0185bdeee94294502f223 +size 1864467848 diff --git a/model-00008-of-00009.safetensors b/model-00008-of-00009.safetensors new file mode 100644 index 0000000..92a1bef --- /dev/null +++ b/model-00008-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6868a9cb0f73d7db3c518eea9993abac0d4eb201f267d75191ce5a62c0147eaf +size 1068046456 diff --git a/model-00009-of-00009.safetensors b/model-00009-of-00009.safetensors new file mode 100644 index 0000000..d0bc46a --- /dev/null +++ b/model-00009-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06006972c3be88e8a44fe21cfe2b0472b130780c781a741f8f90f1fe5ba3aae2 +size 1089994880 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..c924429 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,346 @@ +{ + "metadata": { + "total_size": 15231233024 + }, + "weight_map": { + "lm_head.weight": "model-00009-of-00009.safetensors", + "model.embed_tokens.weight": "model-00001-of-00009.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.14.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.17.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.18.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.27.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.norm.weight": "model-00008-of-00009.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..51ebb3b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa +size 11421896 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..2f20f72 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,208 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833